Performance space searching method and device of adjustable system, equipment and medium

Abstract

The embodiment of the invention discloses a performance space searching method and device of an adjustable system, equipment and a medium. Initializing according to the value range of each parameter in the key parameter set to obtain the current parameter value and the current parameter change trend of each parameter; obtaining a system output result of the adjustable system according to the current parameter value of each parameter; performing performance evaluation on the system output result corresponding to the current parameter value of each parameter according to a preset optimization strategy to obtain a performance evaluation result; determining an update weight of a current parameter change trend of each parameter according to each performance evaluation result, and updating the current parameter change trend according to the update weight; current parameter values are updated according to the updated current parameter change trends; and iteratively returning to the step of determining the system output result according to the parameter values, and determining the optimal performance subspace of the adjustable system according to the parameter values of the parameters when the search termination condition is met. The spatial search efficiency and applicability can be improved by updating the weight to adjust the parameter change trend.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a performance space search method, device, equipment and medium for an adjustable system. Background Art

[0002] With the development of artificial intelligence technology, the demand for computing power has increased dramatically, and the complexity of artificial intelligence processor architecture has become increasingly higher. The artificial intelligence processor architecture is an adjustable system whose performance is affected by multiple parameters, and the number of parameters affecting its performance is increasing exponentially.

[0003] In an adjustable system, each parameter does not affect the performance of the architecture in a single way, but interacts with each other, causing the optimal performance subspace to have a highly discrete characteristic. As a result, the subspace found by manual parameter adjustment in the existing technology is increasingly difficult to meet the performance requirements of the current computing for adjustable systems. Summary of the invention

[0004] The present invention provides a performance space search method, device, equipment and medium for an adjustable system to improve the search efficiency and applicability of the optimal performance subspace.

[0005] According to one aspect of the present invention, a performance space search method for an adjustable system is provided, the method comprising:

[0006] Initialize the parameters according to the value range of each parameter in the key parameter set that affects the performance of the adjustable system, and obtain the current parameter value of each parameter and the corresponding current parameter change trend;

[0007] Obtaining a system output result corresponding to the adjustable system according to the current parameter value of each parameter in the key parameter set;

[0008] Performing a performance evaluation on the system output results corresponding to the current parameter values ​​of each parameter in the key parameter set according to a preset optimization strategy to obtain a performance evaluation result;

[0009] Determine the update weight of the current parameter change trend of each parameter in the key parameter set according to each performance evaluation result, and update the corresponding current parameter change trend according to the update weight;

[0010] According to the change trend of each updated current parameter, the current parameter value of the corresponding parameter in the key parameter set is updated;

[0011] Return the current parameter value of each parameter in the key parameter set, obtain the system output result corresponding to the adjustable system, and iterate the step, and determine the optimal performance subspace of the adjustable system according to the parameter value of each parameter in the key parameter set when the search termination condition is met.

[0012] According to another aspect of the present invention, a performance space search device for an adjustable system is provided, the device comprising:

[0013] A parameter initialization module is used to initialize parameters according to the value range of each parameter in the key parameter set that affects the performance of the adjustable system, and obtain the current parameter value of each parameter and the corresponding current parameter change trend;

[0014] A system output result determination module, used to obtain a system output result corresponding to the adjustable system according to the current parameter value of each parameter in the key parameter set;

[0015] A performance evaluation module, used to perform performance evaluation on the system output results corresponding to the current parameter values ​​of each parameter in the key parameter set according to a preset optimization strategy to obtain a performance evaluation result;

[0016] A parameter change trend updating module, used to determine the update weight of the current parameter change trend of each parameter in the key parameter set according to each performance evaluation result, and update the corresponding current parameter change trend according to the update weight;

[0017] A parameter value updating module, used to update the current parameter value of the corresponding parameter in the key parameter set according to the change trend of each updated current parameter;

[0018] The optimal performance subspace determination module is used to return the current parameter value of each parameter in the key parameter set, iterate the system output result step corresponding to the adjustable system, and determine the optimal performance subspace of the adjustable system based on the parameter value of each parameter in the key parameter set when the search termination condition is met.

[0019] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0020] at least one processor; and

[0021] a memory communicatively connected to the at least one processor; wherein,

[0022] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the performance space search method for an adjustable system described in any embodiment of the present invention.

[0023] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the performance space search method of an adjustable system described in any embodiment of the present invention when executed.

[0024] According to another aspect of the present invention, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, the performance space search method of the adjustable system according to any embodiment of the present invention is implemented.

[0025] The technical solution of the embodiment of the present invention is to initialize parameters according to the value range of each parameter in the key parameter set that affects the performance of the adjustable system, thereby obtaining the current parameter value of each parameter and the corresponding current parameter change trend; obtain the system output result corresponding to the adjustable system according to the current parameter value of each parameter in the key parameter set; perform performance evaluation on the system output result corresponding to the current parameter value of each parameter in the key parameter set according to a preset optimization strategy to obtain a performance evaluation result; determine the update weight of the current parameter change trend of each parameter in the key parameter set according to each performance evaluation result, and update the corresponding current parameter change trend according to the update weight; and perform performance evaluation on the system output result corresponding to the current parameter value of each parameter in the key parameter set according to each updated current parameter change trend. , update the current parameter value of the corresponding parameter in the key parameter set; return the current parameter value of each parameter in the key parameter set, and iterate the system output result step corresponding to the adjustable system. According to the parameter value of each parameter in the key parameter set when the search termination condition is met, the optimal performance subspace of the adjustable system is determined, which solves the optimal performance subspace search problem of the adjustable system such as the processor architecture. By updating the weight adjustment of the parameter change trend according to the performance evaluation result, and then adjusting the parameters to search the optimal performance subspace, the search efficiency and applicability of the optimal performance subspace can be improved, and the problem that manual parameter adjustment cannot achieve the optimal performance subspace search when the performance subspace is highly discrete is overcome.

[0026] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0028] Figure 1 is a flow chart of a performance space search method for an adjustable system provided in accordance with Embodiment 1 of the present invention;

[0029] Figure 2 is a display diagram of a performance subspace provided according to Embodiment 1 of the present invention;

[0030] Figure 3 is a flow chart of another performance space search method for an adjustable system provided according to the first embodiment of the present invention;

[0031] Figure 4 is a flow chart of a performance space search method for an adjustable system provided in accordance with Embodiment 2 of the present invention;

[0032] Figure 5 This is a schematic diagram of updating weight values ​​when CT is greater than or equal to SBA provided in Embodiment 2 of the present invention;

[0033] Figure 6 is a schematic diagram of convergence results of an adjustable system provided according to Embodiment 2 of the present invention;

[0034] Figure 7 This is a schematic diagram comparing the search effects of various performance subspaces provided according to the second embodiment of the present invention;

[0035] Figure 8 is a schematic diagram of the structure of a performance space search device for an adjustable system provided in accordance with Embodiment 3 of the present invention;

[0036] Fig. 9 It is a structural schematic diagram of an electronic device for implementing the performance space search method of an adjustable system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0037] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0038] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0039] Embodiment 1

[0040] Figure 1 This is a flowchart of a performance space search method for an adjustable system provided according to Embodiment 1 of the present invention. This embodiment is applicable to the case of searching for the optimal performance subspace of an adjustable system such as a processor architecture through parameter adjustment. The method can be executed by a performance space search device for the adjustable system. The performance space search device for the adjustable system can be implemented in the form of hardware and / or software. The performance space search device for the adjustable system can be configured in an electronic device, which can be a computer, a server, etc.

[0041] The adjustable system Xsystem can be a hardware architecture such as a processor architecture, a model or a server cluster, etc. The performance space of the adjustable system is highly nonlinear and complex, and its performance is affected by a large number of discrete parameters with a wide range of values ​​and their combinations, forming multiple discretely distributed optimal performance subspaces. Figure 2 is a display diagram of a performance subspace provided according to the first embodiment of the present invention. Figure 2 As shown, the performance subspace of the adjustable system has a multi-peak and multi-valley structure. Based on the multi-peak and multi-valley characteristics of the performance subspace of the adjustable system, the traditional performance subspace search method or the adjustment strategy relying on manual experience has limitations in processing the optimal performance subspace of the adjustable system. The technical solution provided by the embodiment of the present invention can solve the above problems and search for the optimal performance subspace of the adjustable system. Figure 1 As shown, the method includes:

[0042] Step 110 , initializing parameters according to the value range of each parameter in the key parameter set that affects the performance of the adjustable system, and obtaining the current parameter value of each parameter and the corresponding current parameter change trend.

[0043] Specifically, the adjustable system has a series of configuration parameters (System Config Parameters, SysCfgParam), which can be adjusted to make the system work in the best state. In the adjustable system, there are many kinds of configuration parameters. Configuration parameters include both key parameters that directly affect the performance of the adjustable system and some irrelevant and non-influential system default parameters that must be configured.

[0044] In an embodiment of the present invention, all key parameters that affect the performance of the adjustable system can be identified based on a preset system operating state target combined with a statistical analysis method. The key parameters together with the system default parameters constitute a key parameter set. Table 1 is an exemplary key parameter set. For example, when the adjustable system is a register transfer level (RTL) simulation, the optimal performance in the prefetch scenario in the hardware architecture is used as the optimization target of the adjustable system. At this time, the key parameters that can be obtained through key impact parameter identification (KIPI) are. The key parameters in the RTL simulation and the default parameters can together constitute a key parameter set as shown in Table 1. Among them, the KIPI method is not specifically limited and can be implemented according to neural network model analysis, parameter entity recognition, or artificial experience analysis.

[0045] For each parameter in the key parameter set, the parameters can be initialized according to their value ranges to obtain the current parameter values ​​of each parameter and the corresponding current parameter change trends. For example, the current parameter value can be obtained by random initialization within the parameter value range. The current parameter change trend can be randomly initialized under a preset parameter adjustment step size according to the parameter value range.

[0046] Table 1

[0047]

[0048] Optionally, parameters are initialized according to the value range of each parameter in the key parameter set that affects the performance of the adjustable system to obtain the current parameter value of each parameter and the corresponding current parameter change trend, including: performing random parameter initialization according to the value range of each parameter in the key parameter set that affects the performance of the adjustable system to obtain the current parameter value of each parameter; obtaining the current parameter change trend of each parameter according to the value range of each parameter, the preset parameter adjustment step and the random coefficient.

[0049] For example, the parameter value range is The preset parameter adjustment step can be set to 0.1, and the random coefficient is Indicates that the value is in the range of [-1,1]. The current parameter change trend can be expressed as , 0.1 and interval The product of the length of . Through adaptive parameter initialization, the optimization process can flexibly cope with optimization problems under different parameter quantities and scenarios.

[0050] In the embodiment of the present invention, in order to fully consider the discreteness and volatility of the adjustable system when performing subspace search, an intelligent discrete multi-peak multi-valley transformer (IDMMV-Transformer) can be used to expand the features of the configuration parameters. The IDMMV-Transformer can be composed of a variety of functions that can express the performance change trend.

[0051] Optionally, before obtaining the system output result corresponding to the adjustable system based on the current parameter value of each parameter in the key parameter set, it also includes: using multiple preset functions to perform discrete multi-peak and multi-valley feature capture expansion on the current parameter value of each parameter in the key parameter set to obtain the expanded and updated current parameter value of each parameter in the key parameter set.

[0052] The preset function may be a mathematical transformation function in different forms. The preset function includes but is not limited to a power function, a trigonometric function, an exponential function, etc. The feature capture and expansion of the current parameter value by using the preset function for discrete multi-peaks and multi-valleys may refer to capturing the relationship between the parameters by the preset function, performing feature expansion on the parameters, and forming a multi-dimensional feature value. For example, for the parameter and , can be obtained by the formula Feature capture expansion is performed to obtain the current parameter values ​​after expansion and update of each parameter. Through the feature capture expansion of discrete multi-peaks and multi-valleys, the rich features in the performance discrete transformation can be better captured and expressed, and the expression ability of feature data can be enhanced, which is more conducive to searching the optimal performance subspace.

[0053] For example, the key parameter set SysCfgParam Set includes N configuration parameters SysCfgParam, and there are a total of P key parameters that affect performance. Through the feature capture expansion of discrete multi-peaks and multi-valleys, each configuration parameter SysCfgParam can be represented as a P-dimensional vector as the eigenvalue of the configuration parameter. Among them, each eigenvalue can have a corresponding value range. For example, for the configuration parameter The current parameter value of can be expressed as , where each eigenvalue in the vector can be randomly selected from the eigenvalues. Configuration parameters Corresponding current parameter change trend can be expressed as a P-dimensional vector, such as Assume that the upper and lower boundaries of the jth feature are Indicates that The initialization position can be obtained by OK. Among them, is a random coefficient, the value is in the range of [-1,1], 0.1 is the preset parameter adjustment step, The value range of the parameter.

[0054] In the present invention, the configuration parameters in the adjustable system can be discrete values. In order to be able to process discrete input values ​​while avoiding precision loss and conversion complexity when processing discrete problems, the current parameter values ​​can be trimmed and approximated to obtain discrete current parameter values.

[0055] Exemplarily, the current parameter value can be trimmed and approximated by placing all features in a unified dimensional space through an encoding and decoding framework to ensure the uniformity and coordination of the update of each configuration parameter in each feature dimension. For example, the trimming and approximation of the current parameter value (0.2, 1.7, 13.2) can be performed by placing all features in a unified dimensional space through an encoding and decoding framework to obtain the discrete current parameter value (0, 2, 13). Thus, it can be ensured that the optimal performance subspace search of the adjustable system can directly process discrete input data.

[0056] Step 120: Obtain a system output result corresponding to the adjustable system according to the current parameter value of each parameter in the key parameter set.

[0057] The adjustable system corresponds to a system output result for the parameter configuration in the key parameter set. By inputting the current parameter value of each parameter in the key parameter set into the adjustable system, the corresponding system output result (SystemOutput, SysOutput) can be obtained.

[0058] Taking RTL simulation as an adjustable system as an example, the system output results obtained through KPTI can be the chip read and write bandwidth range (Chip Read and Write Bandwidth Peak to Peak, ChipPtp), cluster read and write bandwidth range (Cluster Read and Write Bandwidth Peak to Peak, ClusterPtp), and total bandwidth (TotalBandwidth, TotalBw).

[0059] Step 130: Perform a performance evaluation on the system output results corresponding to the current parameter values ​​of each parameter in the key parameter set according to a preset optimization strategy to obtain a performance evaluation result.

[0060] Among them, the preset optimization policy (System Optimization Policy, SysOptPolicy) can be determined according to the specific adjustable system and the specific performance that the user is concerned about. Exemplarily, the preset optimization policy can be the determination of one or more performance targets in the system output results, that is, the key performance target identification (Key Performance Target Identification, KPTI). In different adjustable systems or different application scenarios, the preset optimization policies will be different. When faced with multiple interrelated or contradictory performance goals, it is necessary to balance the weights and priorities between the goals and flexibly respond to performance optimization goals in different scenarios. For example, for the Prefetch scenario performance in the RTL simulation architecture, the preset optimization strategy combined with the system output results can be The system output results can be evaluated for performance through the preset optimization strategy to obtain the performance evaluation results.

[0061] Step 140: determine the update weight of the current parameter change trend of each parameter in the key parameter set according to each performance evaluation result, and update the corresponding current parameter change trend according to the update weight.

[0062] Among them, by determining the update weight of the current parameter change trend of the corresponding parameter according to the performance evaluation result, the collaborative relationship between the configuration parameters can be considered to realize dynamic exploration of the performance space, and the search range can be adjusted according to the performance evaluation result until the optimal performance subspace is approached or reached.

[0063] When determining the update weight of the current parameter change trend based on the performance evaluation result, when the performance evaluation result is large, a smaller update weight can be used to ensure sufficient search around parameters in the field close to or located in the global optimal solution to ensure refined search capabilities; when the performance evaluation result is small, a larger update weight can be used to promote accelerated convergence to the global optimal solution.

[0064] The current parameter change trend can be updated according to the update weight. For example, the product of the update weight and the current parameter change trend is used as the updated current parameter change trend. By dynamically adjusting the update weight, the current parameter change trend is adjusted to ensure that the optimal performance subspace is searched quickly and accurately.

[0065] Step 150: Update the current parameter values ​​of the corresponding parameters in the key parameter set according to the change trends of the updated current parameters.

[0066] For example, the sum of the current parameter value of the corresponding parameter in the key parameter set and the updated current parameter change trend can be used as the updated current parameter value. , the updated current parameter value is .in, is the current parameter value in the tth iteration. is the current parameter change trend at the t+1th iteration.

[0067] Step 160, return to step 120 to iterate, and determine the optimal performance subspace of the adjustable system according to the parameter value of each parameter in the key parameter set when the search termination condition is met.

[0068] In order to ensure that the optimal performance subspace can be searched, steps 120 to 150 may be iterated multiple times. The optimal performance subspace of the adjustable system is determined in the system output results obtained by the multiple iterations. For example, the search termination condition may be reaching a preset maximum number of iterations. When the maximum number of iterations is reached, the parameter values ​​of each parameter in the key parameter set corresponding to the maximum value of the system output result may be used as the optimal performance subspace of the adjustable system.

[0069] In an optional implementation of an embodiment of the present invention, the optimal performance subspace of the adjustable system is determined based on the parameter values ​​of each parameter in the key parameter set when the search termination condition is met, including: when the maximum number of iterations is reached, determining whether the global optimal performance evaluation result of each parameter in the key parameter set in the iteration, and / or the global optimal system output result in the iteration, meet the preset acceptance condition; when the global optimal performance evaluation result and / or the global optimal system output result meet the preset acceptance condition, the optimal performance subspace of the adjustable system is obtained according to the parameter values ​​of each parameter in the key parameter set corresponding to the global optimal performance evaluation result and / or the global optimal system output result.

[0070] The preset acceptance condition may be the minimum requirement of the performance subspace. When the global best performance evaluation result and / or the global best system output result meet the preset acceptance condition, the adjustable system configuration may be performed according to the parameter values ​​of each parameter in the key parameter set corresponding to the global best performance evaluation result and / or the global best system output result to obtain the optimal performance subspace. If the global best performance evaluation result and / or the global best system output result do not meet the preset acceptance condition, the process may return to step 110, start a new round of iteration, and search the optimal performance subspace.

[0071] Figure 3 FIG. 1 is a flow chart of another method for searching the performance space of an adjustable system according to Embodiment 1 of the present invention. Figure 3As shown, the search process of the optimal performance subspace can be: KIPI identification is performed on the adjustable system to obtain key parameters. Then the key parameters and the default parameters constitute a key parameter set. For each parameter in the key parameter set, a range can be defined to obtain a value range. Among them, the range definition includes the maximum value, minimum value and value calculation method of each parameter. According to the value range, each parameter can be adaptively initialized to obtain the current parameter value of each parameter and the corresponding current parameter change trend. The current parameter value of each parameter and the corresponding current parameter change trend can be input into IDMMV-Transformer for discrete multi-peak and multi-valley feature capture expansion to obtain the current parameter value of each parameter and the corresponding current parameter change trend. The current parameter value after expansion and update of each parameter can be input into the adjustable system to obtain the system output result corresponding to the adjustable system. The system output result can be evaluated by a preset optimization strategy to obtain a performance evaluation result. Among them, the preset optimization strategy can be generated comprehensively according to multiple key performance objectives. According to the performance evaluation result, the weight can be updated to determine, and then the current parameter change trend and the current parameter value can be updated to search the performance subspace. After searching the performance subspace, it is determined whether the search termination condition is met. If the search termination condition is not met, the iteration will continue. If the search termination condition is met, the optimal parameter value corresponding to the optimal performance evaluation result can be obtained, and then the optimal performance subspace of the adjustable system can be determined. Figure 3 The performance space search method of the adjustable system (Intelligent Search Method of Best Performance Subspace, ISMBPS) shown in the figure automatically segments words and iteratively generates the next round of key parameter sets based on the feedback of the system output results. Through continuous iteration, the system optimization goal is achieved, which can comprehensively improve the applicability of the best performance subspace searched in complex hardware architectures and improve the search efficiency.

[0072] The technical solution of this embodiment is to obtain the current parameter value of each parameter and the corresponding current parameter change trend by initializing the parameters according to the value range of each parameter in the key parameter set that affects the performance of the adjustable system; obtain the system output result corresponding to the adjustable system according to the current parameter value of each parameter in the key parameter set; perform performance evaluation on the system output result corresponding to the current parameter value of each parameter in the key parameter set according to the preset optimization strategy to obtain the performance evaluation result; determine the update weight of the current parameter change trend of each parameter in the key parameter set according to each performance evaluation result, and update the corresponding current parameter change trend according to the update weight; and perform the performance evaluation on the key parameter set according to each updated current parameter change trend. The current parameter values ​​of the corresponding parameters in the key parameter set are updated; the current parameter values ​​of the parameters in the key parameter set are returned, and the system output result steps corresponding to the adjustable system are obtained for iteration. According to the parameter values ​​of the parameters in the key parameter set when the search termination condition is met, the optimal performance subspace of the adjustable system is determined, which solves the optimal performance subspace search problem of the adjustable system such as the processor architecture. By updating the weight adjustment of the parameter change trend according to the performance evaluation results, and then adjusting the parameters for the optimal performance subspace search, the search efficiency and applicability of the optimal performance subspace can be improved, and the problem that manual parameter adjustment cannot achieve the optimal performance subspace search when the performance subspace is highly discrete is overcome.

[0073] Embodiment 2

[0074] Figure 4 1 is a flow chart of a performance space search method for an adjustable system provided according to Embodiment 2 of the present invention. This embodiment is a further refinement of the above technical solution. The technical solution in this embodiment can be combined with various optional solutions in one or more of the above embodiments. Figure 4 As shown, the method includes:

[0075] Step 410: Initialize parameters according to the value range of each parameter in the key parameter set that affects the performance of the adjustable system, and obtain the current parameter value of each parameter and the corresponding current parameter change trend.

[0076] In an optional implementation of an embodiment of the present invention, parameters are initialized according to the value range of each parameter in the key parameter set that affects the performance of the adjustable system to obtain the current parameter value of each parameter and the corresponding current parameter change trend, including: performing random parameter initialization according to the value range of each parameter in the key parameter set that affects the performance of the adjustable system to obtain the current parameter value of each parameter; obtaining the current parameter change trend of each parameter according to the value range of each parameter, the preset parameter adjustment step size and the random coefficient.

[0077] Step 420: Use a variety of preset functions to perform discrete multi-peak and multi-valley feature capture expansion on the current parameter value of each parameter in the key parameter set to obtain the expanded and updated current parameter value of each parameter in the key parameter set.

[0078] Step 430: Obtain a system output result corresponding to the adjustable system according to the current parameter value of each parameter in the key parameter set.

[0079] Step 440: Perform a performance evaluation on the system output results corresponding to the current parameter values ​​of the parameters in the key parameter set according to a preset optimization strategy to obtain a performance evaluation result.

[0080] Step 450: Determine the update weight of the current parameter change trend of each parameter in the key parameter set according to each performance evaluation result.

[0081] In an optional implementation, the update weight of the current parameter change trend of each parameter in the key parameter set is determined according to each performance evaluation result, including: when CT is greater than or equal to SBA and the current iteration is the first stage iteration, the update weight of the current parameter change trend corresponding to the target parameter is determined according to the weight threshold, CT, SBA, GB and SA; when CT is greater than SBA and the current iteration is the second stage iteration, the update weight of the current parameter change trend corresponding to the target parameter is determined according to the weight threshold, the current number of iterations and the maximum number of iterations; wherein the first stage iteration is before the second stage iteration; when SA is less than or equal to CT and CT is less than SBA, the lower limit of the weight threshold is used as the update weight of the current parameter change trend corresponding to the target parameter; when CT is less than SA, the upper limit of the weight threshold is used as the update weight of the current parameter change trend corresponding to the target parameter.

[0082] Among them, CT is the performance evaluation result corresponding to the target parameter in the key parameter set in the current iteration (CurrentSysOptTarget, CT), SBA is the average of the historical best performance evaluation results of each parameter in the key parameter set in each iteration (SysCfgParam Set Best Average, SBA), GB is the global best performance evaluation result of each parameter in the key parameter set in the iteration (Global Best SysCfgParam Set SysOptTarget, GB), and SA is the average performance evaluation result of each parameter in the key parameter set in each iteration (SysCfgParam Set SysOptTarget Average, SA).

[0083] In an embodiment of the present invention, the update weight of the current parameter change trend can be divided into three types according to the performance evaluation results, and four methods are determined under these three types. Specifically, the key parameter set can be divided into an elite class, a medium fitness class, and a poor fitness class according to the performance evaluation results. Among them, the elite class key parameter set refers to a large performance evaluation result, for example, CT is greater than or equal to SBA. The medium fitness class key parameter set refers to a performance evaluation result at a medium level, for example, SA is less than or equal to CT, and CT is less than SBA. The poor fitness class key parameter set refers to a low performance evaluation result, for example, CT is less than SA.

[0084] In the embodiment of the present invention, when the performance evaluation result is larger, the update weight can be smaller; when the performance evaluation result is smaller, the update weight can be larger, thereby ensuring that the search convergence is accelerated while ensuring the global search capability.

[0085] In the elite key parameter set, the method of determining the update weight can be divided into two cases, namely the first half of the iteration and the second half of the iteration. Among them, the first half of the iteration is the first stage iteration, and the second half of the iteration is the second stage iteration. In the first stage iteration, a larger update weight can be determined to maintain the global search capability and avoid premature convergence of the optimization process. According to the weight threshold, CT, SBA, GB and SA, the update weight of the current parameter change trend corresponding to the target parameter can be determined when CT is greater than or equal to SBA and the current iteration is the first stage iteration. Exemplarily, when CT is greater than or equal to SBA and the current iteration is the first stage iteration, the value of the update weight can be 1 to 1.5.

[0086] Optionally, when CT is greater than or equal to SBA and the current iteration is the first stage iteration, the update weight of the current parameter change trend corresponding to the target parameter is determined according to the weight threshold, CT, SBA, GB and SA, including: when CT is greater than or equal to SBA and the current iteration is the first stage iteration, the update weight of the current parameter change trend corresponding to the target parameter is determined by the formula Determine the update weight of the current parameter change trend corresponding to the target parameter. Among them, To update the weights, is the preset minimum value for updating weights, The preset maximum value for updating weights.

[0087] In the second stage iteration, the update weight can be gradually reduced to ensure that the update weight does not exceed the preset maximum value of the update weight and is not lower than the preset minimum value of the update weight, so as to enhance the local refined search capability and promote a more detailed search near the potential optimal solution, thereby increasing the probability of finding the global optimal solution.

[0088] Optionally, when CT is greater than SBA and the current iteration is the second stage iteration, the update weight of the current parameter change trend corresponding to the target parameter is determined according to the weight threshold, the current iteration number and the maximum iteration number, including: when CT is greater than SBA and the current iteration is the second stage iteration, the update weight of the current parameter change trend corresponding to the target parameter is determined according to the formula , determine the update weight of the current parameter change trend corresponding to the target parameter. Among them, clip is a function that limits the value range, that is, Less than When , the update weight is taken as ;exist Greater than When , the update weight is taken as ;exist Between and When , the update weight is taken as .

[0089] Figure 5 FIG. 1 is a schematic diagram of updating the weight when CT is greater than or equal to SBA according to Embodiment 2 of the present invention. Figure 5 As shown in the first iteration, since the update weight value is relatively large and changes with its own parameter value, its fitness value may decrease when exploring more solution spaces, or even no longer meet the requirements. As the iteration enters the second stage, the update weight gradually decreases and stabilizes, accelerating the convergence to the global optimal solution.

[0090] When SA is less than or equal to CT, and CT is less than SBA, the lower limit of the weight threshold is As the update weight of the current parameter change trend corresponding to the target parameter, the local search accuracy can be improved, and these parameters can be quickly converged to a better fitness value, thus becoming part of the elite key parameter set.

[0091] When CT is less than SA, the upper limit of the weight threshold is The updated weight of the current parameter change trend corresponding to the target parameter can enhance the global search capability and avoid premature convergence to the local optimal solution, which helps the parameters escape the local optimal solution and explore a wider solution space, thereby increasing the possibility of finding the global optimal solution.

[0092] In an embodiment of the present invention, update weights are determined based on current performance evaluation results and historical performance evaluation results, which can provide a strong global search capability in the early stage and significantly enhance the local fine exploration capability in the later stage of optimization, thereby comprehensively improving the applicability and efficiency of searching in complex hardware performance optimization problems.

[0093] Step 460: Update the corresponding current parameter change trend according to the update weight.

[0094] In an optional implementation of an embodiment of the present invention, the corresponding current parameter change trend is updated according to the update weight, including: determining a first update value of the current parameter change trend corresponding to the target parameter according to the update weight and the current parameter change trend corresponding to the target parameter; determining a second update value of the current parameter change trend corresponding to the target parameter according to the individual optimal parameter value of the target parameter in each iteration in the key parameter set, the current parameter value of the target parameter, and the self-parameter adjustment factor; determining a third update value of the current parameter change trend corresponding to the target parameter according to the global optimal parameter value of the target parameter in each iteration in the key parameter set, the current parameter value of the target parameter, and the group parameter adjustment factor; updating the current parameter change trend corresponding to the target parameter according to the first update value, the second update value and the third update value.

[0095] Among them, the first update value can be the product of the update weight and the current parameter change trend. The second update value can be the difference between the individual optimal parameter value and the current parameter value of the target parameter, multiplied by the own parameter adjustment factor. When determining the second update value, a random coefficient can also be added. The third update value can be the difference between the global optimal parameter value and the current parameter value of the target parameter, multiplied by the group parameter adjustment factor. When determining the third update value, a random coefficient can also be added. The sum of the first update value, the second update value and the third update value can be used as the updated current parameter change trend corresponding to the target parameter.

[0096] For example, the updated current parameter change trend can be expressed by the formula OK. Among them, is the parameter at the t+1th iteration The corresponding current parameter change trend; For parameters The individual optimal parameter value of is the parameter at the tth iteration The current parameter value of is the parameter adjustment factor, is the population parameter adjustment factor, is the global optimal parameter value in the key parameter set, is the maximum number of iterations.

[0097] When updating the current parameter change trend, the system can track its own experience through the individual best parameter value, the current parameter value of the target parameter and its own parameter adjustment factor; it can track the group experience through the global best parameter value, the current parameter value of the target parameter and the group parameter adjustment factor. By updating itself according to its own experience and group experience, it can adjust the parameter value according to the overall information, deeply explore the interaction between individual parameters and the comprehensive impact of the overall key parameter set, and achieve comprehensive and detailed optimization of the adjustable system, thus fundamentally solving the problem that the traditional parameter adjustment method is easy to fall into the local optimum and it is difficult to fully consider the complex interaction between parameters.

[0098] Step 470: Update the current parameter values ​​of the corresponding parameters in the key parameter set according to the change trends of the updated current parameters.

[0099] Step 480: trim and approximate the updated current parameter values ​​of each parameter to obtain discrete current parameter values.

[0100] Step 490, return to step 430 to iterate, and determine the optimal performance subspace of the adjustable system according to the parameter value of each parameter in the key parameter set when the search termination condition is met.

[0101] Optionally, the optimal performance subspace of the adjustable system is determined based on the parameter values ​​of each parameter in the key parameter set when the search termination condition is met, including: when the maximum number of iterations is reached, determining whether the global optimal performance evaluation result of each parameter in the key parameter set in the iteration, and / or the global optimal system output result in the iteration, meet the preset acceptance condition; when the global optimal performance evaluation result and / or the global optimal system output result meet the preset acceptance condition, obtaining the optimal performance subspace of the adjustable system based on the parameter values ​​of each parameter in the key parameter set corresponding to the global optimal performance evaluation result and / or the global optimal system output result.

[0102] The technical solution of the embodiment of the present invention can better represent the parameters by expanding the feature capture of discrete multi-peaks and multi-valleys of the current parameter values ​​of each parameter, adapt to the discreteness and volatility of the adjustable system performance space, enhance the expressiveness of the feature data, and capture the discrete multi-peaks and multi-valley characteristics of the performance space by developing more complex data generation and enhancement pipelines, making it easier to be used by subsequent analysis and models. By determining the update weight according to the size of the performance evaluation results and the stage of the iteration, the update weight is adaptively adjusted to generate a flexible search mechanism and an efficient optimization strategy; in the early stage of iterative optimization, in order to quickly locate the approximate area of ​​the global optimal solution, a larger update weight value can be used to enhance the global search capability; as the iteration proceeds, the weight value is gradually reduced, and the focus is turned to local fine exploration to improve the accuracy and stability of the solution; the dynamic weight adjustment strategy ensures that both efficient global search capabilities and fine local optimization can be maintained during the optimization process. By considering the update weights, individual parameter influences, and group parameter influences when updating the current parameter change trend, the collaborative working mode of the group can be simulated. Through the interaction and collaboration between parameters, a comprehensive and detailed optimization of the complex adjustable system can be achieved, fundamentally solving the problem that the traditional system parameter tuning method is prone to fall into the local optimum and is difficult to fully consider the complex interactions between parameters. The reliability of the optimal performance subspace can be guaranteed through the upper-level verification of the maximum number of iterations and the preset acceptance conditions. By trimming and approximating the current parameter values, the discrete input parameter values ​​can be processed to achieve the unification of multi-dimensional parameters, avoiding the accuracy loss or conversion complexity that may occur in the traditional continuous optimization method when dealing with discrete problems. Therefore, the technical solution of the embodiment of the present invention solves the problem of searching the optimal performance subspace of an adjustable system such as a processor architecture, can improve the search efficiency and applicability of the optimal performance subspace, and overcome the problem that manual parameter adjustment cannot achieve the optimal performance subspace search when the performance subspace is highly discrete.

[0103] Through the above-mentioned performance space search method of the adjustable system, after multiple iterations, the adjustable system reaches convergence. Figure 6 FIG. 1 is a schematic diagram of convergence results of an adjustable system provided according to the second embodiment of the present invention. Figure 6 As shown in the figure, the performance space search method of the adjustable system successfully identifies and approaches the local optimum near the optimal subspace, which reflects the stability and excellent performance of the performance subspace search.

[0104] The performance space search method of the adjustable system provided by the embodiment of the present invention has excellent performance compared with the manual tuning method in the prior art. Figure 7 FIG. 1 is a schematic diagram comparing the search effects of various performance subspaces provided according to Embodiment 2 of the present invention. Figure 7As shown in the figure, the vertical axis is TotalBw, and the horizontal axis is the ratio of the maximum and minimum chip read and write bandwidth (Chip Read and Write Bandwidth Peak to Peak Ratio, ChipPtpRatio). A higher TotalBw value and a lower ChipPtpRatio indicate that the adjustable system has better performance.

[0105] Figure 7 The distribution of blue data points corresponding to manual parameter adjustment in the figure shows a convergence bottleneck when approaching the optimal performance area in the upper left corner, indicating that manual parameter adjustment faces significant challenges when trying to optimize peak performance and coverage at the same time, and can often only achieve optimization effects for a single goal. In contrast, the distribution of orange data points obtained by tuning using the optimal performance subspace search method provided in the embodiment of the present invention generally shows superiority over manual parameter adjustment in terms of peak performance. Not only that, the method of the embodiment of the present invention has also successfully discovered many performance points that can break through the bottleneck of manual parameter adjustment, and found an optimized configuration solution that can take into account both peak performance and coverage. This comparison result not only highlights the significant advantages of the method of the embodiment of the present invention and its necessity in practical applications, but also further emphasizes the urgent need to solve large-scale engineering optimization problems.

[0106] The performance space search method for the adjustable system provided by the embodiment of the present invention has shown extremely high practicality and innovation in the field of performance optimization, and can be used to guide multiple links such as system architecture tuning and system performance evaluation, providing strong support for improving the market competitiveness of system products. At the same time, its efficiency and flexibility also provide new ideas and methods for solving complex optimization problems in other fields. Especially for hardware architecture tuning, it solves problems that traditional methods cannot solve, and alleviates the need for massive investment in equipment and manpower.

[0107] Embodiment 3

[0108] Figure 8 1 is a schematic diagram of the structure of a performance space search device for an adjustable system according to Embodiment 3 of the present invention. Figure 8 As shown, the device includes: a parameter initialization module 810, a system output result determination module 820, a performance evaluation module 830, a parameter change trend update module 840, a parameter value update module 850 and an optimal performance subspace determination module 860. Among them:

[0109] The parameter initialization module 810 is used to initialize the parameters according to the value range of each parameter in the key parameter set that affects the performance of the adjustable system, and obtain the current parameter value of each parameter and the corresponding current parameter change trend;

[0110] The system output result determination module 820 is used to obtain the system output result corresponding to the adjustable system according to the current parameter value of each parameter in the key parameter set;

[0111] The performance evaluation module 830 is used to perform a performance evaluation on the system output results corresponding to the current parameter values ​​of each parameter in the key parameter set according to a preset optimization strategy to obtain a performance evaluation result;

[0112] The parameter change trend updating module 840 is used to determine the update weight of the current parameter change trend of each parameter in the key parameter set according to each performance evaluation result, and update the corresponding current parameter change trend according to the update weight;

[0113] A parameter value updating module 850 is used to update the current parameter value of the corresponding parameter in the key parameter set according to the change trend of each updated current parameter;

[0114] The optimal performance subspace determination module 860 is used to return the current parameter value of each parameter in the key parameter set, iterate the system output result step corresponding to the adjustable system, and determine the optimal performance subspace of the adjustable system based on the parameter value of each parameter in the key parameter set when the search termination condition is met.

[0115] Optionally, the device further includes:

[0116] The feature capture expansion module is used to use a variety of preset functions to perform discrete multi-peak and multi-valley feature capture expansion on the current parameter values ​​of each parameter in the key parameter set before obtaining the system output result corresponding to the adjustable system based on the current parameter values ​​of each parameter in the key parameter set, so as to obtain the current parameter values ​​of each parameter in the key parameter set after expansion and update.

[0117] Optionally, the parameter change trend updating module 840 includes:

[0118] A first update weight determination unit, configured to determine an update weight of a current parameter change trend corresponding to a target parameter according to a weight threshold, CT, SBA, GB, and SA when CT is greater than or equal to SBA and the current iteration is a first-stage iteration;

[0119] Among them, CT is the performance evaluation result corresponding to the target parameter in the key parameter set in the current iteration, SBA is the average of the historical best performance evaluation results of each parameter in the key parameter set in each iteration, GB is the global best performance evaluation result of each parameter in the key parameter set in the iteration, and SA is the average performance evaluation result of each parameter in the key parameter set in each iteration;

[0120] A second update weight determination unit is used to determine the update weight of the current parameter change trend corresponding to the target parameter according to the weight threshold, the current iteration number and the maximum iteration number when CT is greater than SBA and the current iteration is the second stage iteration; wherein the first stage iteration is before the second stage iteration;

[0121] A third update weight determination unit, configured to use the lower limit of the weight threshold as the update weight of the current parameter change trend corresponding to the target parameter when SA is less than or equal to CT and CT is less than SBA;

[0122] The fourth update weight determination unit is used to use the upper limit of the weight threshold as the update weight of the current parameter change trend corresponding to the target parameter when CT is less than SA.

[0123] Optionally, the parameter change trend updating module 840 includes:

[0124] A first update value determination unit, configured to determine a first update value of a current parameter change trend corresponding to the target parameter according to the update weight and the current parameter change trend corresponding to the target parameter;

[0125] A second update value determination unit, configured to determine a second update value of a current parameter change trend corresponding to the target parameter according to the individual best parameter value of the target parameter in each iteration in the key parameter set, the current parameter value of the target parameter, and the own parameter adjustment factor;

[0126] A third update value determination unit, configured to determine a third update value of the current parameter change trend corresponding to the target parameter according to the global optimal parameter value of the target parameter in each iteration in the key parameter set, the current parameter value of the target parameter, and the group parameter adjustment factor;

[0127] The parameter change trend updating unit is used to update the current parameter change trend corresponding to the target parameter according to the first update value, the second update value and the third update value.

[0128] Optionally, the optimal performance subspace determination module 860 includes:

[0129] A preset acceptance condition verification unit is used to determine, when the maximum number of iterations is reached, whether the global best performance evaluation result of each parameter in the key parameter set in the iteration and / or the global best system output result in the iteration meets the preset acceptance condition;

[0130] The optimal performance subspace determination unit is used to obtain the optimal performance subspace of the adjustable system according to the parameter values ​​of each parameter in the key parameter set corresponding to the global best performance evaluation result and / or the global best system output result when the global best performance evaluation result and / or the global best system output result meet the preset acceptance conditions.

[0131] Optionally, the device further includes:

[0132] The trimming and approximation module is used to trim and approximate the current parameter values ​​of each parameter after updating the current parameter values ​​of the corresponding parameters in the key parameter set according to the change trends of the updated current parameters to obtain discrete current parameter values.

[0133] Optionally, the parameter initialization module 810 includes:

[0134] A parameter value initialization unit, used to perform random parameter initialization according to the value range of each parameter in the key parameter set that affects the performance of the adjustable system, and obtain the current parameter value of each parameter;

[0135] The parameter change trend initialization unit is used to obtain the current parameter change trend of each parameter according to the value range of each parameter, the preset parameter adjustment step size and the random coefficient.

[0136] The performance space search device for an adjustable system provided in an embodiment of the present invention can execute the performance space search method for an adjustable system provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0137] Embodiment 4

[0138] Fig. 9 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0139] like Fig. 9As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. The input / output (I / O) interface 15 is also connected to the bus 14.

[0140] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0141] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the performance space search method of the adjustable system.

[0142] In some embodiments, the performance space search method for an adjustable system may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. Optionally, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the performance space search method for an adjustable system described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the performance space search method for an adjustable system in any other appropriate manner (e.g., by means of firmware).

[0143] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0144] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0145] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, device, or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0146] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0147] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0148] A computing system may include a client and a server. The client and the server are generally remote from each other and often interact through a communication network. The relationship between the client and the server is generated by computer programs running on the respective computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0149] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. The steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document is not limited here.

[0150] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A performance space search method for an adjustable system, characterized in that: include: Initialize the parameters according to the value range of each parameter in the key parameter set that affects the performance of the adjustable system, and obtain the current parameter value of each parameter and the corresponding current parameter change trend; Obtaining a system output result corresponding to the adjustable system according to the current parameter value of each parameter in the key parameter set; Performing a performance evaluation on the system output results corresponding to the current parameter values ​​of each parameter in the key parameter set according to a preset optimization strategy to obtain a performance evaluation result; Determine the update weight of the current parameter change trend of each parameter in the key parameter set according to each performance evaluation result, and update the corresponding current parameter change trend according to the update weight; According to the change trend of each updated current parameter, the current parameter value of the corresponding parameter in the key parameter set is updated; Return the current parameter value of each parameter in the key parameter set, obtain the system output result corresponding to the adjustable system, and iterate the step, and determine the optimal performance subspace of the adjustable system according to the parameter value of each parameter in the key parameter set when the search termination condition is met.

2. The method according to claim 1, characterized in that: Before obtaining the system output result corresponding to the adjustable system according to the current parameter value of each parameter in the key parameter set, the method further includes: A plurality of preset functions are used to perform discrete multi-peak and multi-valley feature capture expansion on the current parameter value of each parameter in the key parameter set, so as to obtain the expanded and updated current parameter value of each parameter in the key parameter set.

3. The method according to claim 1, characterized in that: Determining the update weight of the current parameter change trend of each parameter in the key parameter set according to each performance evaluation result includes: When CT is greater than or equal to SBA and the current iteration is the first phase iteration, the update weight of the current parameter change trend corresponding to the target parameter is determined according to the weight threshold, CT, SBA, GB and SA; Wherein, CT is the performance evaluation result corresponding to the target parameter in the key parameter set in the current iteration, SBA is the average value of the best historical performance evaluation results of each parameter in the key parameter set in each iteration, GB is the global best performance evaluation result of each parameter in the key parameter set in the iteration, and SA is the average performance evaluation result of each parameter in the key parameter set in each iteration; When CT is greater than SBA and the current iteration is the second-stage iteration, the update weight of the current parameter change trend corresponding to the target parameter is determined according to the weight threshold, the current iteration number and the maximum iteration number; wherein the first-stage iteration is before the second-stage iteration; When SA is less than or equal to CT, and CT is less than SBA, the lower limit of the weight threshold is used as the update weight of the current parameter change trend corresponding to the target parameter; When CT is less than SA, the upper limit of the weight threshold is used as the update weight of the current parameter change trend corresponding to the target parameter.

4. The method according to claim 1, characterized in that Updating the corresponding current parameter change trend according to the update weight includes: Determining a first update value of the current parameter change trend corresponding to the target parameter according to the update weight and the current parameter change trend corresponding to the target parameter; Determine a second updated value of the current parameter change trend corresponding to the target parameter according to the individual optimal parameter value of the target parameter in each iteration in the key parameter set, the current parameter value of the target parameter, and the own parameter adjustment factor; Determine a third updated value of the current parameter change trend corresponding to the target parameter according to the global optimal parameter value of the target parameter in each iteration in the key parameter set, the current parameter value of the target parameter, and the population parameter adjustment factor; According to the first update value, the second update value and the third update value, the current parameter change trend corresponding to the target parameter is updated.

5. The method according to claim 1, characterized in that: According to the parameter value of each parameter in the key parameter set when the search termination condition is met, the optimal performance subspace of the adjustable system is determined, including: When the maximum number of iterations is reached, determining whether the global best performance evaluation result of each parameter in the key parameter set in the iteration and / or the global best system output result in the iteration meets a preset acceptance condition; When the global best performance evaluation result and / or the global best system output result meet the preset acceptance conditions, the optimal performance subspace of the adjustable system is obtained according to the parameter values ​​of each parameter in the key parameter set corresponding to the global best performance evaluation result and / or the global best system output result.

6. The method according to claim 1, characterized in that After updating the current parameter value of the corresponding parameter in the key parameter set according to the updated current parameter change trend, the method further includes: The updated current parameter values ​​of each parameter are trimmed and approximated to obtain discrete current parameter values.

7. The method according to claim 1, characterized in that Parameters are initialized according to the value range of each parameter in the key parameter set that affects the performance of the adjustable system, and the current parameter value of each parameter and the corresponding current parameter change trend are obtained, including: Performing random parameter initialization according to the value range of each parameter in the key parameter set that affects the performance of the adjustable system, and obtaining the current parameter value of each parameter; According to the value range of each parameter, the preset parameter adjustment step size and the random coefficient, the current parameter change trend of each parameter is obtained.

8. A performance space search device for an adjustable system, characterized in that: include: A parameter initialization module is used to initialize parameters according to the value range of each parameter in the key parameter set that affects the performance of the adjustable system, and obtain the current parameter value of each parameter and the corresponding current parameter change trend; A system output result determination module, used to obtain a system output result corresponding to the adjustable system according to the current parameter value of each parameter in the key parameter set; A performance evaluation module, used to perform performance evaluation on the system output results corresponding to the current parameter values ​​of each parameter in the key parameter set according to a preset optimization strategy to obtain a performance evaluation result; A parameter change trend updating module, used to determine the update weight of the current parameter change trend of each parameter in the key parameter set according to each performance evaluation result, and update the corresponding current parameter change trend according to the update weight; A parameter value updating module, used to update the current parameter value of the corresponding parameter in the key parameter set according to the change trend of each updated current parameter; The optimal performance subspace determination module is used to return the current parameter value of each parameter in the key parameter set, iterate the system output result step corresponding to the adjustable system, and determine the optimal performance subspace of the adjustable system based on the parameter value of each parameter in the key parameter set when the search termination condition is met.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the performance space search method of the adjustable system according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the performance space search method of the adjustable system according to any one of claims 1 to 7 when executed.

Images